本文へ移動
cccskills
無料GitHub で公開

extension-store-assets

Generates browser extension brand icons, Chrome Web Store promo tiles, promotional screenshots, brand guides, and listing copy. Uses OpenRouter gpt-image-2 via lib/blog-image-generator. Use when creating extension branding, Chrome Web Store assets, app icon concepts, store descriptions, or /extension-store-assets workflows.

日本語の概要は準備中です。原文の説明を表示しています。

Illyism/dev-skillsスター 18(GitHub 18 + cccskills 0)

実行スコア 未検証

インストール方法を見る

含まれるファイル(6)

  • SKILL.md4.8 KB
  • brand.config.example.json2.5 KB
  • product-details-template.md724 B
  • prompts.md4.3 KB
  • scripts/generate.ts8.5 KB
  • sizes.md1.2 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Extension store assets

Three-phase workflow for extension branding + Chrome Web Store listing. Self-contained script uses OpenRouter gpt-image-2 directly (no blog-image-generator dependency).

Phases

PhaseGoalOutput
1. ConceptsExplore 4–6 unrelated brand directionsconcept-*.jpg (1:1) + preview.html
2. Pick + refineUser picks one; delete losers; optional brand guideapp-icon.jpg, brand-guide.jpg
3. StorePromo tiles, promo slides, listing copystore/*

Do not skip phase 1. Do not generate literal UI screenshots for store slides — use promotional concept slides that explain benefits.

Setup

  1. Copy brand.config.example.json → {outputDir}/brand.config.json
  2. Fill in product name, brand prompt prefix, colors, concept prompts, store slide prompts
  3. Run from repo root with env loaded

Commands

set -a && source .env && set +a && bun .cursor/skills/extension-store-assets/scripts/generate.ts --config=public/store-assets/brand.config.json --phase=concepts

set -a && source .env && set +a && bun .cursor/skills/extension-store-assets/scripts/generate.ts --config=public/store-assets/brand.config.json --phase=brand-guide

set -a && source .env && set +a && bun .cursor/skills/extension-store-assets/scripts/generate.ts --config=public/store-assets/brand.config.json --phase=store

set -a && source .env && set +a && bun .cursor/skills/extension-store-assets/scripts/generate.ts --config=public/store-assets/brand.config.json --phase=store --screenshots-only

After phase 1, user picks a concept → set iconFile in config to that filename → delete other concepts → run phase 2 and 3.

Store asset rules

See sizes.md for exact dimensions.

Promo tiles — generate at closest aspect ratio, fit: cover to exact size.

Store screenshots (1280×800) — promotional benefit slides, NOT fake browser/extension UI mocks. Generate at 16:9, scale with fit: cover to exact size (full bleed). Set paddingPercent: 0 in config (default).

What makes slides look store-ready (see public/store-assets/store/):

  • Background color/texture fills all four edges — no letterbox margin
  • Decorative elements (glows, class pills, footer bars) bleed off canvas edges
  • Content uses multi-column editorial layout that fills the frame — not a small centered island
  • Concrete UI widgets with sample data (class names, code snippets, button states) — not abstract icon rows alone
  • Contrasting card pairs (before vs after, format A vs format B)
  • Bottom footer bar or three-icon feature row anchors the composition

See prompts.md for per-slide composition templates.

Listing copy — write store/product-details.md using product-details-template.md. Short description ≤132 chars.

Prompt patterns

See prompts.md.

Concept icons: distinct visual worlds — not literal clipboard/marquee dev-tool clichés unless requested. Fun, beautiful, readable at 16px.

Brand guide: 16:9 cheat sheet — palette, typography, UI components, icon usage. Use picked icon as input_reference.

Store slides (5 max): hero value prop → how it works → key benefit → feature depth → format/compare. Concept illustration only.

Do not

  • Edit lib/blog-image-generator/generate.ts
  • Use blog _references/ style refs (raw prompts only)
  • Generate literal screenshots for Chrome store slides
  • Letterbox 1280×800 slides unless paddingPercent > 0 is explicitly set
  • Center small content on a large empty background — use multi-column layouts that fill the frame
  • Abstract icon-only slides with no sample data or UI widgets
  • Skip visual review before shipping

Paths

ItemPath
Generator script.cursor/skills/extension-store-assets/scripts/generate.ts
Example config.cursor/skills/extension-store-assets/brand.config.example.json
Size reference.cursor/skills/extension-store-assets/sizes.md
Copy template.cursor/skills/extension-store-assets/product-details-template.md
Prompt patterns.cursor/skills/extension-store-assets/prompts.md
Worked example configpublic/store-assets/brand.config.json

Worked example

A fictional tab-grouping extension in public/store-assets/: deep navy + amber, stacked-cards metaphor. Store slides: store/screenshot-01-hero through screenshot-05-formats.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

Micro-benchmark and iteratively improve hot paths in any codebase — baseline first, mandatory improvement suggestions (bottleneck + 3 creative ideas + recommended next step), bounded attempts, user lock-in checkpoints, then human WHY comments after lock-in. Use when the user asks to benchmark, profile, optimize performance, compare implementations, or measure µs/op before shipping perf changes. Applies to Bun/Node, React, Next.js, browser code, and extensions.

日本語の概要は準備中です。原文の説明を表示しています。

Illyism/dev-skills182026年10月15日 更新

cleanup

無料

Cleanup code, optimize, refactor, delete the 80% to keep the 20%

日本語の概要は準備中です。原文の説明を表示しています。

Illyism/dev-skills182026年10月15日 更新

elon

無料

Applies the Elon Musk Algorithm to coding, product, SaaS, design, and current issues. Use when the user invokes /elon or requests Elon Musk-style first-principles analysis.

日本語の概要は準備中です。原文の説明を表示しています。

Illyism/dev-skills182026年10月15日 更新

eval

無料

Build, run, or update minimal evaluation benchmarks for AI prompts, LLM calls, multi-model comparisons, and core functions. Use when creating new eval scripts, comparing models side-by-side, filtering specific candidate models, running benchmarks, or inspecting eval.md output artifacts.

日本語の概要は準備中です。原文の説明を表示しています。

Illyism/dev-skills182026年10月15日 更新

optimize

無料

Optimizes code, queries, and features based on actual usage by removing unused fields, aggregations, JOINs, and unused complexity. Use when the user invokes /optimize or asks to slim queries to what the UI actually uses.

日本語の概要は準備中です。原文の説明を表示しています。

Illyism/dev-skills182026年10月15日 更新

Illyism のスキルをすべて見る

このスキルの問題を報告する